用于三维点云识别的双模块图卷积网络  

Dual-module graph convolutional network for 3D point cloud recognition

作　　者：王博豪 孙战里[1] WANG Bohao;SUN Zhanli(School of Electrical Engineering and Automation,Anhui University,Hefei 230601,China)

机构地区：[1]安徽大学电气工程与自动化学院,安徽合肥230601

出　　处：《传感器与微系统》2022年第9期132-135,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61972002)。

摘　　要：针对三维点云识别的无序性且缺乏拓扑信息的问题。设计了一种双模块图卷积神经网络,能够同时学习点云的多尺度特征和残差特征,以提高三维(3D)点云的识别精度。在第一个模块中,利用基于修正余弦相似度的图卷积,以及不同的特征维度,提取点云的多尺度特征。在第二个模块中,利用多层网络间的跨层连接,以及固定尺度邻域图,提取点云残差特征。将两种特征融合,作为多层感知机的输入,经过池化层和全连接层网络,对点云进行分类。在公开数据集ModelNet40上的实验结果,证明了该算法的有效性。Aiming at the problem of disorder and lack of topological information of 3 D point cloud recognition, a dual module graph convolutional neural network is devised to improve 3 D point cloud recognition accuracy, by learning both multi-scale features and residual features of point cloud.In the first module, the multi-scale features are extracted via graph convolution based on adjusted cosine similarity and different feature dimensions.In the second module, the residual features of point cloud are extracted by the skip connections of multi-layer networks and the fixed-scale neighborhood graphs.Then, two kinds of features are fused as the input of multilayer perceptron(MLP).Finally, the point cloud is classified via a pooling layer and fully connected layers.The experimental results on the public available dataset ModelNet40 demonstrate the effectiveness of the proposed approach.

关 键 词：三维点云 点云识别 邻域图 余弦相似度 图卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]